Natural Language Processing in Automation
summary
Overview of concrete results and tools: code and notebooks live on GitHub, models use BERT and RoBERTa for classification and generation tasks, and pipelines for machine translation, knowledge‑base search, social‑media trend detection and developer virtual assistants are prototyped as APIs. Claims: GPT‑style models lack true understanding, show bias, have no realtime knowledge and give incorrect math answers (reported as ~100% failure on arithmetic), typical NLP systems reach ~70–80% accuracy. Ongoing projects include explainable sexism detection and an AI judge evaluation with train/validation/test splits.
AI-written summary · about
chapters (8)
- 0:00Introduction
- 0:32Agenda
- 1:28Machine Learning
- 2:40NLP
- 5:56Examples
- 8:35Trends
- 10:44GPT
- 14:13dissertations
related talks
55mDemystifying Natural Language Processing across several industry verticals
12mUnlocking the Power of NLP: Techniques in K8s-Native Applications
26mNatural Language Processing for Healthcare: Current Trends...
23mUnveiling the Journey of NLP
06mAdvancements in Natural Language Processing (NLP) and Text Analytics
15mNatural Language-Guided Programming
21mData-Driven NLP: From Statistics to GenAI
26mNatural Language Processing (NLP) going mainstream